IEEE WORKSHOP ON CONTENT-BASED ACCESS OF
                     IMAGE AND VIDEO LIBRARIES

                   (In Conjunction with CVPR'97)

                           Puerto Rico
                          June 20, 1997

General Chair: 
  Rosalind W. Picard, MIT Media Lab

Organizing Committee: 
  Fang Liu, chair; Glenn Healey, Michael Swain, Ramin Zabih

Program Committee:
  Ingemar Cox, Dick Delanoy, David Forsyth, Anil Jain, Ramesh Jain,
  Takeo Kanade, Rangachar Kasturi, B.S. Manjunath, Wayne Niblack, 
  Alex Pentland, Harpreet Sawhney, Stan Sclaroff, Linda Shapiro, 
  Rohini Srihari, Carlo Tomasi, HongJiang Zhang


The purpose of this workshop is to promote information exchange and
interaction among researchers who are interested in various aspects of
accessing the content of image and video libraries.

Research in computer vision and pattern recognition is needed to
provide tools which give users access to the content of the libraries.
This includes the problems of ORGANIZING, REPRESENTING, QUERYING,
RETRIEVING, ANNOTATING, and BROWSING large collections of video and
image data.  The domain of video and image libraries also restates the
typical automatic recognition problem as a semi-automatic problem,
that of assisting and incorporating human users in the system loop.

NEW REPRESENTATIONS are needed to assist users in interacting with
large amounts of visual data, especially for video, which presents the
challenging problems which arise in demarcating events or actions of
interest.

Research is needed to exploit the PRESENCE OF THE USER, such as
obtaining incremental specifications for a query and using user
feedback to combine semantic, perceptual, and other criteria in
evaluating the results of a query.

A research emphasis is needed on INCORPORATING MULTIPLE MODELS,
especially the ones for shape, color, texture, geometry, and syntax,
so that the user does not have to specify low-level model parameters
and combinations.

When databases and types of queries can be well-specified in advance,
then strategies of EFFICIENT INDEXING of visual information are
needed, in addition to techniques for combining visual with more
traditional database information to respond to queries.

Realistic EVALUATION CRITERIA are needed, including test
databases of realistic size in domains of interest, and measures of
similarity that allow variations in perceptual, semantic, and other
criteria and including measures of accuracy and efficiency in
assisting the user.

The workshop will be held on 20 June, the day after CVPR'97.  Hotel
rates for CVPR'97 have been extended.  Papers submitted will be
reviewed by the program committee. A proceedings will be made
available a few months after the workshop.

Submissions should be 5-8 pages in the format of final papers for CVPR
proceedings, including figures and references.  There should not be
substantial duplication between papers submitted to the workshop and
those accepted at the main conference.  Send four copies of the paper
and a cover sheet stating the (1) paper title, (2) Brief (2-3
sentence) summary of the topic and contribution, (3) contact author's
name, (4) address, (5) telephone number, (6) Fax number, and (7)
electronic mail address to:

                        Fang Liu
                        E15-390, MIT Media Lab
                        20 Ames St.
                        Cambridge, MA 02139
                        U.S.A.

Important Dates:

               Deadline for Submission: 24 March 1997
            Notification of Acceptance: 28 April 1997
               Camera-ready Papers Due: 26 May 1997


The workshop homepage is at http://www.cs.uchicago.edu/~swain/cfp-ivl.html

Sponsored by the PAMI Technical Committee of the IEEE Computer Society